isAlbertYu / AI-FlappyBirdLinks
基于深度强化学习DQN的FlappyBird游戏AI开发
☆15Updated 6 years ago
Alternatives and similar repositories for AI-FlappyBird
Users that are interested in AI-FlappyBird are comparing it to the libraries listed below
Sorting:
- 引用整理https://blog.csdn.net/yellow_red_people/article/details/80465510 一文中PyTorch平台，利用DQN模型玩Flappy Bird游戏，是一个再励学习（强化学习）实验例子。☆50Updated 6 years ago
- 用强化学习DQN算法，训练AI模型来玩合成大西瓜游戏，提供Keras版本和PARL（paddle）版本☆95Updated 4 years ago
- Deep Q-Network (DQN) and DDPG to address the problem of stall around the wing sail of an autonomous sailing robot☆11Updated 7 years ago
- lecture32_AI挑战星际争霸II（强化学习）☆18Updated 3 years ago
- 用parl框架的DQN强化学习算法玩“合成大西瓜”☆14Updated 4 years ago
- 一款基于DQN算法的牌类游戏AI框架 / An AI framework for card games based on DQN algorithm☆13Updated last year
- 人工智能导论课程设计-用强化学习玩FlappyBird☆18Updated 5 years ago
- ☆11Updated 3 years ago
- Real time image capture+DQN path planning☆11Updated 2 years ago
- 本项目以一个可视化配置的、以AgentRL为核心的强化学习框架，实现30分钟上手AgentRL 编程。后续增加AgentRL和本地Agent、MCP、A2A相关特性。☆77Updated 5 months ago
- 深度强化学习贪吃蛇游戏。拥有完整游戏环境与AI接口。（项目未完成）☆40Updated 6 years ago
- DQN model used to train and beat Super Mario Bros. for the NES using PyTorch☆35Updated 3 years ago
- 主要利用QLearning,DQN,ImprovedDQN(Ddouble DQN) 解决gym框架下的三个问题CartPole-v0,MountainCar-v0,Acrobot-v1☆13Updated 7 years ago
- 通过python3.6编程，利用DQN算法实现机器学习避开障碍走到迷宫终点。（Through python3.6 programming, I use DQN algorithm to achieve machine learning and avoid obstacles…☆10Updated 7 years ago
- 使用pytorch构建深度强化学习模型DQN☆26Updated 8 years ago
- DQN深度强化学习解决三维在线装箱问题☆30Updated 2 years ago
- 学习DRL CNN -> DQN -> LSTM☆13Updated 7 years ago
- 通过深度强化学习训练的AI玩起游戏来也是有板有眼，将人类玩家远远甩在身后。本文就将为您介绍如何训练AI玩微信飞机大战，biubiubiu~☆24Updated 6 years ago
- a simple USV game model☆12Updated 6 years ago
- Deep Q Network for Multi-agent RL☆15Updated 5 years ago
- 白话强化学习与PyTorch的学习笔记☆37Updated 5 years ago
- 车杆倒立摆DQN简单实现☆24Updated 5 months ago
- AI项目（强化学习、深度学习、计算机视觉、推荐系统、自然语言处理、机器导航、医学影像处理）☆92Updated 2 years ago
- Multi-Exit Evacuation simulation; Rainbow DQN application☆17Updated 5 years ago
- pytorch, noisy_distributional_double_dueling_PER_RNN_CNN...CartPole-v1 , Acrobot-v1, MountainCar-v0☆15Updated 7 years ago
- 在PyTorch上重构multi-agent deep deterministic policy gradient(MADDPG)，将https://github.com/xuemei-ye/maddpg-mpe 修改到自己电脑上可运行。因为本人笔记本没有CUDA，实验速度…☆14Updated 6 years ago
- 强化学习-中文笔记&资源-以python实例为主-由浅入深☆109Updated 5 years ago
- DQN flappy bird with tensorflow2☆16Updated 4 years ago
- 一个遗传算法实现，用于对一组GPS数据点进行线路规划，规划依据为线路路径最短。☆21Updated 2 years ago
- Part of a research scholarship. I built a basic 2d driving sim with simulated lidar data to train Deep Q Neural Network. So far after abo…☆11Updated 8 years ago